Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4063 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1350828 (The Pile)

Max Activating Token Index: 962

Text #1

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3999. Min Act: -0.0000

Data Index: 460623 (The Pile)

Max Activating Token Index: 1005

Text #2

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3971. Min Act: -0.0000

Data Index: 1379087 (The Pile)

Max Activating Token Index: 217

Text #3

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.4037. Min Act: -0.0000

Data Index: 1402110 (The Pile)

Max Activating Token Index: 846

Text #4

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3433. Min Act: -0.0000

Data Index: 934769 (The Pile)

Max Activating Token Index: 397

Text #5

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3485. Min Act: -0.0000

Data Index: 769866 (The Pile)

Max Activating Token Index: 490

Text #6

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3641. Min Act: -0.0000

Data Index: 358273 (The Pile)

Max Activating Token Index: 898

Text #7

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3243. Min Act: -0.0000

Data Index: 758488 (The Pile)

Max Activating Token Index: 171

Text #8

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3213. Min Act: -0.0000

Data Index: 762994 (The Pile)

Max Activating Token Index: 455

Text #9

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3202. Min Act: -0.0000

Data Index: 643560 (The Pile)

Max Activating Token Index: 325

Text #10

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3440. Min Act: -0.0000

Data Index: 794046 (The Pile)

Max Activating Token Index: 455

Text #11

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3089. Min Act: -0.0000

Data Index: 619537 (The Pile)

Max Activating Token Index: 757

Text #12

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3077. Min Act: -0.0000

Data Index: 1267393 (The Pile)

Max Activating Token Index: 903

Text #13

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2983. Min Act: -0.0000

Data Index: 634224 (The Pile)

Max Activating Token Index: 657

Text #14

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3154. Min Act: -0.0000

Data Index: 482644 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2887. Min Act: -0.0000

Data Index: 1521486 (The Pile)

Max Activating Token Index: 191

Text #16

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2774. Min Act: -0.0000

Data Index: 1626020 (The Pile)

Max Activating Token Index: 678

Text #17

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3036. Min Act: -0.0000

Data Index: 1847519 (The Pile)

Max Activating Token Index: 977

Text #18

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2685. Min Act: -0.0000

Data Index: 88799 (The Pile)

Max Activating Token Index: 735

Text #19

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2752. Min Act: -0.0000

Data Index: 641102 (The Pile)

Max Activating Token Index: 585